Xiangxin Meng (孟祥鑫)

Profile

I am currently a researcher at the Software Engineering Laboratory of ByteDance, focusing on research related to LLM4Code. I completed both my undergraduate and doctoral studies at the School of Computer Science and Engineering at Beihang University (SCSE, BUAA), obtaining a Bachelor of Engineering degree in June 2018 and a Doctor of Engineering degree in June 2024. During my PhD, I was advised by Professor Xudong Liu and Associate Professor Xu Wang, exploring areas such as neural network-based bug detection, fault localization, and automated program repair. During my doctoral studies, I had the privilege of closely collaborating with Professor Hongyu Zhang from Chongqing University on various research projects.

My current research interests mainly focus on enhancing code-related tasks using large language models and AI Agents, including next-generation AI Agent-based code generation, bug reproduction, fault localization, and program repair, etc.

Publications

Improving fault localization and program repair with deep semantic features and transferred knowledge

Improving fault localization and program repair with deep semantic features and transferred knowledge

Xiangxin Meng, Xu Wang*, Hongyu Zhang, Hailong Sun, Xudong Liu

ICSE 2022

ABSHTMLPDFCODE
Template-based neural program repair

Template-based neural program repair

Xiangxin Meng, Xu Wang*, Hongyu Zhang, Hailong Sun, Xudong Liu, Chunming Hu

ICSE 2023

ABSHTMLPDFCODE
MTL-TRANSFER: Leveraging Multi-task Learning and Transferred Knowledge for Improving Fault Localization and Program Repair

MTL-TRANSFER: Leveraging Multi-task Learning and Transferred Knowledge for Improving Fault Localization and Program Repair

Xu Wang, Hongwei Yu, Xiangxin Meng*, Hongliang Cao, Hongyu Zhang, Hailong Sun, Xudong Liu, Chunming Hu

TOSEM 2024

ABSCODE
Element-Based Automated DNN Repair with Fine-Tuned Masked Language Model

Element-Based Automated DNN Repair with Fine-Tuned Masked Language Model

Xu Wang, Mingming Zhang, Xiangxin Meng*, Jian Zhang, Yang Liu, Chunming Hu

FSE 2025

CODE
(Distinguished Paper Award) An empirical study on fine-tuning large language models of code for automated program repair

(Distinguished Paper Award) An empirical study on fine-tuning large language models of code for automated program repair

Kai Huang, Xiangxin Meng, Jian Zhang*, Yang Liu, Wenjie Wang, Shuhao Li, Yuqing Zhang

ASE 2023

ABSHTMLPDFCODE
Template-guided program repair in the era of large language models

Template-guided program repair in the era of large language models

Kai Huang, Jian Zhang*, Xiangxin Meng, Yang Liu

ICSE 2025

ABSHTMLPDFCODE
Improving Vulnerability Detection with Hybrid Code Graph Representation

Improving Vulnerability Detection with Hybrid Code Graph Representation

Xiangxin Meng, Shaoxiao Lu, Xu Wang*, Xudong Liu, Chunming Hu

APSEC 2023

ABSHTMLPDF